© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116753
    Prev
    Next
    INDEX
    Explanations

    Mardi Gras masquerades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aventura
    -0.93
    紅葉
    -0.87
    tivas
    -0.82
    MATCH
    -0.82
    OptionsMenu
    -0.80
    rals
    -0.80
    chymal
    -0.80
     haza
    -0.80
     Wimbledon
    -0.79
     fawn
    -0.79
    POSITIVE LOGITS
     Mardi
    1.40
     Carnival
    1.36
     carnival
    1.29
     parade
    1.19
     parades
    1.18
    Carnival
    1.13
    Mardi
    1.07
     February
    1.05
    february
    1.03
     costumes
    0.99
    Activations Density 0.012%

    No Known Activations